whatmodel.sh / xLAM-2-32b-fc-r

xLAM-2-32b-fc-r

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

xLAM-2-32b-fc-r is an open-weights language model from Salesforce, released March 2025. Its published size is 32.76B parameters. Licence: cc-by-nc-4.0.

Catalogue identity notes

Maker repo Salesforce/xLAM-2-32b-fc-r @5ddef33: licence tag cc-by-nc-4.0. 32,763,876,352 parameters from the Hugging Face safetensors metadata (dense, so active = total). Released 2025-03: month the maker's Hugging Face repo was created (createdAt 2025-03-27).

66.4±3.9#130 of 949 LLMsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The LLMs ranked either side of xLAM-2-32b-fc-r, out of 1132 with a score, then more from Salesforce.

#modelscorewhereRAMreleased
163Qwen3 235B-A22B Thinking 2507 Alibaba66±1api $0.97/M +local~76GB2025-07
164Grok 4.1 Fast (Reasoning) SpaceXAI (xAI)66±1api $0.28/M2025-11
165xLAM-2-32b-fc-r Salesforce66±4local~21GB2025-03
166o4-mini OpenAI66±1api $1.93/M2025-04
167Nova 2 Omni (Preview) Amazon66±7api $0.93/M2025-11
more from Salesforce
170Llama-xLAM-2-70b-fc-r Salesforce66±4local~29GB2025-03
256Llama-xLAM-2-8b-fc-r Salesforce62±4local~6.6GB2025-03
350xLAM-2-3b-fc-r Salesforce58±4local~3.5GB2025-03

see all LLMs · find the ones that fit your machine

$ what it's good at

agent tasks▁▁▃▆█▆▅▄▄▃▂▁ #143 of 334 * · 93% of its score · 2 tests

Beats watt-tool-70B, Qwen3 235B-A22B Thinking 2507 here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Large, GPT-4o (2024-05-13) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
BFCL V4 (December 2025 archive)54.7% ✎▁▁▁▂██▅▅▆▂▂▂ beats 64/77hard · avg 32%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%at its level
BFCL v376.4% ✎▁▁▁▁▁▃▅█▅▄▁▃ beats 113/114medium · avg 52%▇▇▇▇▇▇▇▇▇▇ 26%blunt · at its level

$ where to run it

llama.cpp · recommended

version

  1. Install llama.cpp · Homebrew and winget installs name the commands llama-cli and llama-server instead.
    macOS / Linux
    curl -LsSf https://llama.app/install.sh | sh
    Windows
    irm https://llama.app/install.ps1 | iex

    other ways to install ↗

  2. Run xLAM-2-32b-fc-r · needs ~19.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    llama cli -hf mradermacher/xLAM-2-32b-fc-r-GGUF:Q4_K_M
  3. Or start a local server and open the address it prints (http://localhost:9931)
    llama serve -hf mradermacher/xLAM-2-32b-fc-r-GGUF:Q4_K_M

LM Studio

version

  1. Install LM Studio · Open the app once before using the lms command.

    download it (macOS / Windows / Linux) ↗

  2. Run xLAM-2-32b-fc-r · needs ~19.9 GB · from huggingface.co/mradermacher

    open in LM Studio ↗

  3. Or download it in the terminal
    lms get https://huggingface.co/mradermacher/xLAM-2-32b-fc-r-GGUF@Q4_K_M -y
  4. Then run lms ls to see its name, and lms chat followed by that name

Ollama

version

  1. Install Ollama

    download it (macOS / Windows) ↗

    Linux
    curl -fsSL https://ollama.com/install.sh | sh
  2. Run xLAM-2-32b-fc-r · needs ~19.9 GB · from huggingface.co/mradermacher
    chat in the terminal
    ollama run hf.co/mradermacher/xLAM-2-32b-fc-r-GGUF:Q4_K_M

MLX (Mac)

version

  1. Install MLX (Mac) · Apple silicon Macs only, text only.
    with uv
    uv tool install mlx-lm
    or
    pip install mlx-lm
  2. Run xLAM-2-32b-fc-r · needs ~18.4 GB, Mac only · from huggingface.co/mxmcc
    chat in the terminal
    mlx_lm.chat --model mxmcc/xLAM-2-32b-fc-r-4bit
  3. Or start an OpenAI-compatible server at http://localhost:8080/v1
    mlx_lm.server --model mxmcc/xLAM-2-32b-fc-r-4bit

Other ways to run it

  1. Run it as published · needs ~65.53 GB · from huggingface.co/Salesforce (official)
    uv run --with torch --with 'transformers<5' --with accelerate python -c "from transformers import pipeline; print(pipeline('text-generation', model='Salesforce/xLAM-2-32b-fc-r', torch_dtype='auto', device_map='auto')('Once upon a time', max_new_tokens=40)[0]['generated_text'])"

Official weights and documentation: huggingface.co/Salesforce ↗

$ how the score was worked out · Berkeley Function Calling Lea… 93%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
Berkeley Function Calling Leaderboard result archive2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%Apache-2.0
prior · pull toward the middle▇▇ 7%
weighted average= 66.4

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json